Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 16-GEMMASCOPE-RES-16K
    6. 12774
    Prev
    Next
    INDEX
    Explanations

    temporal phrases and transitions in narrative contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    following prepositions or conjunctions

    np_acts-logits-general · gemini-2.0-flash

    after a state or event

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     InputDecoration
    -0.58
     thiệu
    -0.52
     spades
    -0.51
     specchio
    -0.49
    agissait
    -0.47
    naphthal
    -0.47
    ึง
    -0.46
     lusso
    -0.46
    rdı
    -0.46
     SEGU
    -0.45
    POSITIVE LOGITS
    OGND
    0.75
    RenderAtEndOf
    0.68
     recent
    0.68
    BeginContext
    0.66
     beginnetje
    0.66
    Билгалдахарш
    0.62
     оригіналу
    0.62
    GOTREF
    0.61
    IndentedString
    0.61
     onAnimation
    0.60
    Activations Density 0.483%

    No Known Activations